Design of interconnection networks for programmable optoelectronic multiprocessor technology

F. Kiamilev, A. Krishnamoorthy, P. Marchand, R. Paturi, Sadik Esener, S. H. Lee

Research output: Contribution to journalArticle

Abstract

Programmable optoelectronic multiprocessor (POEM) architecture is based on wafer-scale integration of optoelectronic processing elements (PEs) and reconfigurable free-space interconnects. Calculations and prototype development show that it is possible to have over 100K simple one-bit PEs per wafer. Since an important architectural feature of a parallel computer is its interconnection network linking the processing elements, the authors evaluate interconnection networks based on POEM technology. They consider various multistage interconnection network topologies such as the perfect shuffle, butterfly, banyan and data manipulator and evaluate how well they map onto the POEM technology. They determine the effects of varying the grain size of the router switches, network control, fault tolerance and interconnection topology on network performance and compare the performance of POEM networks with VLSI-based interconnection networks and the proposed optical digital switch architecture based on symbolic substitution.

Original languageEnglish (US)
Pages (from-to)217-218
Number of pages2
JournalUnknown Journal
Volume1359
StatePublished - 1990
Externally publishedYes

Fingerprint

Optoelectronic devices
Technology
Butterflies
Processing
WSI circuits
Switches
Topology
topology
switches
wafers
network control
fault tolerance
parallel computers
Network performance
Fault tolerance
Routers
Manipulators
very large scale integration
Substitution reactions
manipulators

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Kiamilev, F., Krishnamoorthy, A., Marchand, P., Paturi, R., Esener, S., & Lee, S. H. (1990). Design of interconnection networks for programmable optoelectronic multiprocessor technology. Unknown Journal, 1359, 217-218.

Design of interconnection networks for programmable optoelectronic multiprocessor technology. / Kiamilev, F.; Krishnamoorthy, A.; Marchand, P.; Paturi, R.; Esener, Sadik; Lee, S. H.

In: Unknown Journal, Vol. 1359, 1990, p. 217-218.

Research output: Contribution to journalArticle

Kiamilev, F, Krishnamoorthy, A, Marchand, P, Paturi, R, Esener, S & Lee, SH 1990, 'Design of interconnection networks for programmable optoelectronic multiprocessor technology', Unknown Journal, vol. 1359, pp. 217-218.
Kiamilev F, Krishnamoorthy A, Marchand P, Paturi R, Esener S, Lee SH. Design of interconnection networks for programmable optoelectronic multiprocessor technology. Unknown Journal. 1990;1359:217-218.
Kiamilev, F. ; Krishnamoorthy, A. ; Marchand, P. ; Paturi, R. ; Esener, Sadik ; Lee, S. H. / Design of interconnection networks for programmable optoelectronic multiprocessor technology. In: Unknown Journal. 1990 ; Vol. 1359. pp. 217-218.
@article{f5790e6e3dcb42a88d27fe84c33d87e1,
title = "Design of interconnection networks for programmable optoelectronic multiprocessor technology",
abstract = "Programmable optoelectronic multiprocessor (POEM) architecture is based on wafer-scale integration of optoelectronic processing elements (PEs) and reconfigurable free-space interconnects. Calculations and prototype development show that it is possible to have over 100K simple one-bit PEs per wafer. Since an important architectural feature of a parallel computer is its interconnection network linking the processing elements, the authors evaluate interconnection networks based on POEM technology. They consider various multistage interconnection network topologies such as the perfect shuffle, butterfly, banyan and data manipulator and evaluate how well they map onto the POEM technology. They determine the effects of varying the grain size of the router switches, network control, fault tolerance and interconnection topology on network performance and compare the performance of POEM networks with VLSI-based interconnection networks and the proposed optical digital switch architecture based on symbolic substitution.",
author = "F. Kiamilev and A. Krishnamoorthy and P. Marchand and R. Paturi and Sadik Esener and Lee, {S. H.}",
year = "1990",
language = "English (US)",
volume = "1359",
pages = "217--218",
journal = "Indian Journal of Rheumatology",
issn = "0973-3698",
publisher = "Elsevier (Singapore) Pte Ltd",

}

TY - JOUR

T1 - Design of interconnection networks for programmable optoelectronic multiprocessor technology

AU - Kiamilev, F.

AU - Krishnamoorthy, A.

AU - Marchand, P.

AU - Paturi, R.

AU - Esener, Sadik

AU - Lee, S. H.

PY - 1990

Y1 - 1990

N2 - Programmable optoelectronic multiprocessor (POEM) architecture is based on wafer-scale integration of optoelectronic processing elements (PEs) and reconfigurable free-space interconnects. Calculations and prototype development show that it is possible to have over 100K simple one-bit PEs per wafer. Since an important architectural feature of a parallel computer is its interconnection network linking the processing elements, the authors evaluate interconnection networks based on POEM technology. They consider various multistage interconnection network topologies such as the perfect shuffle, butterfly, banyan and data manipulator and evaluate how well they map onto the POEM technology. They determine the effects of varying the grain size of the router switches, network control, fault tolerance and interconnection topology on network performance and compare the performance of POEM networks with VLSI-based interconnection networks and the proposed optical digital switch architecture based on symbolic substitution.

AB - Programmable optoelectronic multiprocessor (POEM) architecture is based on wafer-scale integration of optoelectronic processing elements (PEs) and reconfigurable free-space interconnects. Calculations and prototype development show that it is possible to have over 100K simple one-bit PEs per wafer. Since an important architectural feature of a parallel computer is its interconnection network linking the processing elements, the authors evaluate interconnection networks based on POEM technology. They consider various multistage interconnection network topologies such as the perfect shuffle, butterfly, banyan and data manipulator and evaluate how well they map onto the POEM technology. They determine the effects of varying the grain size of the router switches, network control, fault tolerance and interconnection topology on network performance and compare the performance of POEM networks with VLSI-based interconnection networks and the proposed optical digital switch architecture based on symbolic substitution.

UR - http://www.scopus.com/inward/record.url?scp=0025558320&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025558320&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0025558320

VL - 1359

SP - 217

EP - 218

JO - Indian Journal of Rheumatology

JF - Indian Journal of Rheumatology

SN - 0973-3698

ER -